INDEX

Explanations

terms related to resource policies and user permissions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nore

-0.16

ofs

-0.15

ow

-0.15

ather

-0.15

ruk

-0.15

uno

-0.14

xes

-0.14

th

-0.14

opensource

-0.14

ere

-0.14

POSITIVE LOGITS

bette

0.16

icken

0.14

oston

0.14

ä¹Ĳ

0.14

icaret

0.14

Ð¾ÐºÐ¸

0.13

alous

0.13

altar

0.13

antz

0.13

utow

0.13

Activations Density 0.087%

terms related to resource policies and user permissions

No Comments

No Known Activations